Linux内存管理之数据结构及转换关系

常用数据结构

1、mm_struct数据结构

mm_struct记录了内存相关的数据结构，包括VMA列表、虚拟缓存队列数、映射区域的基地址、task虚拟地址空间大小、高端虚拟地址的尾地址、VMA数量、用户命名空间信息以及巨页信息（包括原子操作对象）等，该数据结构还有一个钩子函数get_unmmaped_area，用于找到内存中没有映射的区域，由每个架构实现。
该数据结构还有一个比较重要的成员cpu_bitmap，是一个可变长数组，用于记录当前内存节点的cpumask（CPU位图），表示该节点下有哪几个CPU核，最大的情况是UMA架构下的所有CPU，在NUMA下，需要根据具体的节点分布决定。由于该成员是一个可变长数组，因此必须放在数据结构的最后。

struct mm_struct {
	struct {
		struct vm_area_struct *mmap;		/* list of VMAs */
		struct rb_root mm_rb;
		u64 vmacache_seqnum;                   /* per-thread vmacache */
#ifdef CONFIG_MMU
		unsigned long (*get_unmapped_area) (struct file *filp,
				unsigned long addr, unsigned long len,
				unsigned long pgoff, unsigned long flags);
#endif
		unsigned long mmap_base;	/* base of mmap area */
		unsigned long mmap_legacy_base;	/* base of mmap area in bottom-up allocations */
#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
		/* Base adresses for compatible mmap() */
		unsigned long mmap_compat_base;
		unsigned long mmap_compat_legacy_base;
#endif
		unsigned long task_size;	/* size of task vm space */
		unsigned long highest_vm_end;	/* highest vma end address */
		pgd_t * pgd;

#ifdef CONFIG_MEMBARRIER
		/**
		 * @membarrier_state: Flags controlling membarrier behavior.
		 *
		 * This field is close to @pgd to hopefully fit in the same
		 * cache-line, which needs to be touched by switch_mm().
		 */
		atomic_t membarrier_state;
#endif

		/**
		 * @mm_users: The number of users including userspace.
		 *
		 * Use mmget()/mmget_not_zero()/mmput() to modify. When this
		 * drops to 0 (i.e. when the task exits and there are no other
		 * temporary reference holders), we also release a reference on
		 * @mm_count (which may then free the &struct mm_struct if
		 * @mm_count also drops to 0).
		 */
		atomic_t mm_users;

		/**
		 * @mm_count: The number of references to &struct mm_struct
		 * (@mm_users count as 1).
		 *
		 * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
		 * &struct mm_struct is freed.
		 */
		atomic_t mm_count;

		/**
		 * @has_pinned: Whether this mm has pinned any pages.  This can
		 * be either replaced in the future by @pinned_vm when it
		 * becomes stable, or grow into a counter on its own. We're
		 * aggresive on this bit now - even if the pinned pages were
		 * unpinned later on, we'll still keep this bit set for the
		 * lifecycle of this mm just for simplicity.
		 */
		atomic_t has_pinned;

		/**
		 * @write_protect_seq: Locked when any thread is write
		 * protecting pages mapped by this mm to enforce a later COW,
		 * for instance during page table copying for fork().
		 */
		seqcount_t write_protect_seq;

#ifdef CONFIG_MMU
		atomic_long_t pgtables_bytes;	/* PTE page table pages */
#endif
		int map_count;			/* number of VMAs */

		spinlock_t page_table_lock; /* Protects page tables and some
					     * counters
					     */
		struct rw_semaphore mmap_lock;

		struct list_head mmlist; /* List of maybe swapped mm's.	These
					  * are globally strung together off
					  * init_mm.mmlist, and are protected
					  * by mmlist_lock
					  */


		unsigned long hiwater_rss; /* High-watermark of RSS usage */
		unsigned long hiwater_vm;  /* High-water virtual memory usage */

		unsigned long total_vm;	   /* Total pages mapped */
		unsigned long locked_vm;   /* Pages that have PG_mlocked set */
		atomic64_t    pinned_vm;   /* Refcount permanently increased */
		unsigned long data_vm;	   /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
		unsigned long exec_vm;	   /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
		unsigned long stack_vm;	   /* VM_STACK */
		unsigned long def_flags;

		spinlock_t arg_lock; /* protect the below fields */
		unsigned long start_code, end_code, start_data, end_data;
		unsigned long start_brk, brk, start_stack;
		unsigned long arg_start, arg_end, env_start, env_end;

		unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */

		/*
		 * Special counters, in some configurations protected by the
		 * page_table_lock, in other configurations by being atomic.
		 */
		struct mm_rss_stat rss_stat;

		struct linux_binfmt *binfmt;

		/* Architecture-specific MM context */
		mm_context_t context;

		unsigned long flags; /* Must use atomic bitops to access */

		struct core_state *core_state; /* coredumping support */

#ifdef CONFIG_AIO
		spinlock_t			ioctx_lock;
		struct kioctx_table __rcu	*ioctx_table;
#endif
#ifdef CONFIG_MEMCG
		/*
		 * "owner" points to a task that is regarded as the canonical
		 * user/owner of this mm. All of the following must be true in
		 * order for it to be changed:
		 *
		 * current == mm->owner
		 * current->mm != mm
		 * new_owner->mm == mm
		 * new_owner->alloc_lock is held
		 */
		struct task_struct __rcu *owner;
#endif
		struct user_namespace *user_ns;

		/* store ref to file /proc/<pid>/exe symlink points to */
		struct file __rcu *exe_file;
#ifdef CONFIG_MMU_NOTIFIER
		struct mmu_notifier_subscriptions *notifier_subscriptions;
#endif
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
		pgtable_t pmd_huge_pte; /* protected by page_table_lock */
#endif
#ifdef CONFIG_NUMA_BALANCING
		/*
		 * numa_next_scan is the next time that the PTEs will be marked
		 * pte_numa. NUMA hinting faults will gather statistics and
		 * migrate pages to new nodes if necessary.
		 */
		unsigned long numa_next_scan;

		/* Restart point for scanning and setting pte_numa */
		unsigned long numa_scan_offset;

		/* numa_scan_seq prevents two threads setting pte_numa */
		int numa_scan_seq;
#endif
		/*
		 * An operation with batched TLB flushing is going on. Anything
		 * that can move process memory needs to flush the TLB when
		 * moving a PROT_NONE or PROT_NUMA mapped page.
		 */
		atomic_t tlb_flush_pending;
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
		/* See flush_tlb_batched_pending() */
		bool tlb_flush_batched;
#endif
		struct uprobes_state uprobes_state;
#ifdef CONFIG_HUGETLB_PAGE
		atomic_long_t hugetlb_usage;
#endif
		struct work_struct async_put_work;

#ifdef CONFIG_IOMMU_SUPPORT
		u32 pasid;
#endif
	} __randomize_layout;

	/*
	 * The mm_cpumask needs to be at the end of mm_struct, because it
	 * is dynamically sized based on nr_cpu_ids.
	 */
	unsigned long cpu_bitmap[];
};

2、vm_area_struct数据结构

该结构体用得比较多的就是：
（1）vm_start、vm_end：分别记录当前虚拟内存地址空间的起始地址和终止地址，同事用于计算出虚拟地址空间大小；
（2）vm_next、vm_prev：用于遍历每个task的VM内存区域列表；
（3）vm_rb：记录虚拟内存的红黑树结构，在新增内存时会将之添加到该树形结构中，这里涉及到内存结构染色问题，具体不再详述；
（4）vm_mm：每个task归属的mm_struct数据结构，这样可以找到mm_struct想要的数据，一般在做映射、内存节点管理等用得比较多；
（5）vm_page_prot：虚拟内存的访问权限，该成员是一个只有一个u64类型的成员数据结构，常用访问权限有：PROT_READ、PROT_WRITE、PROT_EXEC、PROC_SEM（表示页面内存用于原子操作）、PROT_NONE（页面内存不可访问）、PROT_GROWSDOWN（延伸变化到growsdown VMA的起始位置）、PROT_GROWSUP（延伸变化到growsdown VMA的终止位置）；
（6）vm_flags：虚拟内存操作/访问标志；
（7）vm_ops：每块虚拟内存挂的钩子函数集

struct vm_area_struct {
	/* The first cache line has the info for VMA tree walking. */

	unsigned long vm_start;		/* Our start address within vm_mm. */
	unsigned long vm_end;		/* The first byte after our end address
					   within vm_mm. */

	/* linked list of VM areas per task, sorted by address */
	struct vm_area_struct *vm_next, *vm_prev;

	struct rb_node vm_rb;

	/*
	 * Largest free memory gap in bytes to the left of this VMA.
	 * Either between this VMA and vma->vm_prev, or between one of the
	 * VMAs below us in the VMA rbtree and its ->vm_prev. This helps
	 * get_unmapped_area find a free area of the right size.
	 */
	unsigned long rb_subtree_gap;

	/* Second cache line starts here. */

	struct mm_struct *vm_mm;	/* The address space we belong to. */

	/*
	 * Access permissions of this VMA.
	 * See vmf_insert_mixed_prot() for discussion.
	 */
	pgprot_t vm_page_prot;
	unsigned long vm_flags;		/* Flags, see mm.h. */

	/*
	 * For areas with an address space and backing store,
	 * linkage into the address_space->i_mmap interval tree.
	 */
	struct {
		struct rb_node rb;
		unsigned long rb_subtree_last;
	} shared;

	/*
	 * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
	 * list, after a COW of one of the file pages.	A MAP_SHARED vma
	 * can only be in the i_mmap tree.  An anonymous MAP_PRIVATE, stack
	 * or brk vma (with NULL file) can only be in an anon_vma list.
	 */
	struct list_head anon_vma_chain; /* Serialized by mmap_lock &
					  * page_table_lock */
	struct anon_vma *anon_vma;	/* Serialized by page_table_lock */

	/* Function pointers to deal with this struct. */
	const struct vm_operations_struct *vm_ops;

	/* Information about our backing store: */
	unsigned long vm_pgoff;		/* Offset (within vm_file) in PAGE_SIZE
					   units */
	struct file * vm_file;		/* File we map to (can be NULL). */
	void * vm_private_data;		/* was vm_pte (shared mem) */

#ifdef CONFIG_SWAP
	atomic_long_t swap_readahead_info;
#endif
#ifndef CONFIG_MMU
	struct vm_region *vm_region;	/* NOMMU mapping region */
#endif
#ifdef CONFIG_NUMA
	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
#endif
	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
} __randomize_layout;

3、vm_operations_struct

常用页面内存宏与转换关系

页面内存宏

转换关系